© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1016
    Prev
    Next
    INDEX
    Explanations

    all in all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aleación
    -1.16
     destiné
    -1.09
     graduación
    -1.01
     doté
    -1.01
     rodillas
    -0.99
     fieltro
    -0.98
     tirantes
    -0.96
     calefacción
    -0.96
     déterminé
    -0.96
     vidrio
    -0.94
    POSITIVE LOGITS
     in
    3.67
     told
    2.23
     overall
    1.80
     said
    1.72
     together
    1.69
     altogether
    1.66
    Overall
    1.52
     Overall
    1.47
     insgesamt
    1.40
    together
    1.38
    Activations Density 0.009%

    No Known Activations